Real-time interactive data mining for chemical imaging information: application to automated histopathology.

David Mayerich, Michael Walsh, Matthew Schulmerich, Rohit Bhargava

Research output: Contribution to journalArticle

Abstract

Vibrational spectroscopic imaging is now used in several fields to acquire molecular information from microscopically heterogeneous systems. Recent advances have led to promising applications in tissue analysis for cancer research, where chemical information can be used to identify cell types and disease. However, recorded spectra are affected by the morphology of the tissue sample, making identification of chemical structures difficult. Extracting features that can be used to classify tissue is a cumbersome manual process which limits this technology from wide applicability. In this paper, we describe a method for interactive data mining of spectral features using GPU-based manipulation of the spectral distribution. This allows researchers to quickly identify chemical features corresponding to cell type. These features are then applied to tissue samples in order to visualize the chemical composition of the tissue without the use of chemical stains.

Original languageEnglish (US)
Number of pages1
JournalUnknown Journal
Volume14
DOIs
StatePublished - 2013
Externally publishedYes

Fingerprint

Data Mining
Data mining
Imaging
Tissue
Real-time
Imaging techniques
Spectral Distribution
Heterogeneous Systems
Cell
Manipulation
Cancer
Coloring Agents
Classify
Research Personnel
Technology
Chemical analysis
Research
Neoplasms

ASJC Scopus subject areas

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

Real-time interactive data mining for chemical imaging information : application to automated histopathology. / Mayerich, David; Walsh, Michael; Schulmerich, Matthew; Bhargava, Rohit.

In: Unknown Journal, Vol. 14, 2013.

Research output: Contribution to journalArticle

@article{f0917f9c1c9e4e1d9f5ee6a66b5512aa,
title = "Real-time interactive data mining for chemical imaging information: application to automated histopathology.",
abstract = "Vibrational spectroscopic imaging is now used in several fields to acquire molecular information from microscopically heterogeneous systems. Recent advances have led to promising applications in tissue analysis for cancer research, where chemical information can be used to identify cell types and disease. However, recorded spectra are affected by the morphology of the tissue sample, making identification of chemical structures difficult. Extracting features that can be used to classify tissue is a cumbersome manual process which limits this technology from wide applicability. In this paper, we describe a method for interactive data mining of spectral features using GPU-based manipulation of the spectral distribution. This allows researchers to quickly identify chemical features corresponding to cell type. These features are then applied to tissue samples in order to visualize the chemical composition of the tissue without the use of chemical stains.",
author = "David Mayerich and Michael Walsh and Matthew Schulmerich and Rohit Bhargava",
year = "2013",
doi = "10.1186/1471-2105-14-156",
language = "English (US)",
volume = "14",
journal = "[No source information available]",
issn = "1001-0742",
publisher = "Chinese Academy of Sciences",

}

TY - JOUR

T1 - Real-time interactive data mining for chemical imaging information

T2 - application to automated histopathology.

AU - Mayerich, David

AU - Walsh, Michael

AU - Schulmerich, Matthew

AU - Bhargava, Rohit

PY - 2013

Y1 - 2013

N2 - Vibrational spectroscopic imaging is now used in several fields to acquire molecular information from microscopically heterogeneous systems. Recent advances have led to promising applications in tissue analysis for cancer research, where chemical information can be used to identify cell types and disease. However, recorded spectra are affected by the morphology of the tissue sample, making identification of chemical structures difficult. Extracting features that can be used to classify tissue is a cumbersome manual process which limits this technology from wide applicability. In this paper, we describe a method for interactive data mining of spectral features using GPU-based manipulation of the spectral distribution. This allows researchers to quickly identify chemical features corresponding to cell type. These features are then applied to tissue samples in order to visualize the chemical composition of the tissue without the use of chemical stains.

AB - Vibrational spectroscopic imaging is now used in several fields to acquire molecular information from microscopically heterogeneous systems. Recent advances have led to promising applications in tissue analysis for cancer research, where chemical information can be used to identify cell types and disease. However, recorded spectra are affected by the morphology of the tissue sample, making identification of chemical structures difficult. Extracting features that can be used to classify tissue is a cumbersome manual process which limits this technology from wide applicability. In this paper, we describe a method for interactive data mining of spectral features using GPU-based manipulation of the spectral distribution. This allows researchers to quickly identify chemical features corresponding to cell type. These features are then applied to tissue samples in order to visualize the chemical composition of the tissue without the use of chemical stains.

UR - http://www.scopus.com/inward/record.url?scp=84886821538&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886821538&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-14-156

DO - 10.1186/1471-2105-14-156

M3 - Article

C2 - 23651487

AN - SCOPUS:84886821538

VL - 14

JO - [No source information available]

JF - [No source information available]

SN - 1001-0742

ER -